# Venice

HQ US · datacenters US · serves 36 tracked open-weights models, 33 confirmed by its own catalog. · privacy policy

# models

model	rank	$/M in	$/M out	$/M cache	src	✓
kimi-k3	#1	$3.75	$18.75	—	venice	✓
deepseek-v4-pro	#2	$1.65	$3.30	—	venice	✓
glm-5.2	#3	$1.40	$4.40	—	venice	✓
kimi-k2.6	#4	$0.75	$3.50	—	venice	✓
minimax-m3	#6	$0.30	$1.20	—	venice	✓
kimi-k2.7-code	#7	$0.75	$3.50	—	venice	✓
deepseek-v4-flash	#8	$0.14	$0.28	—	venice	✓
glm-5	#9	$1.00	$3.20	—	venice	✓
glm-5.1	#10	$1.54	$4.84	—	venice	✓
minimax-m2.5	#11	$0.27	$0.95	$0.03	openrouter	—
kimi-k2.5	#12	$0.56	$3.50	—	venice	✓
qwen3.6-27b	#13	$0.33	$3.25	—	venice	✓
glm-4.7	#15	$0.55	$2.65	—	venice	✓
qwen3.6-35b-a3b	#16	$0.10	$1.00	—	venice	✓
qwen3.5-397b-a17b	#17	$0.75	$4.50	—	venice	✓
deepseek-v3.2	#19	$0.33	$0.48	—	venice	✓
qwen3.5-35b-a3b	#23	$0.31	$1.25	—	venice	✓
glm-4.6	#24	$0.43	$1.75	—	venice	✓
gemma-4-31b-it	#25	$0.12	$0.36	—	venice	✓
gemma-4-26b-a4b-it	#27	$0.13	$0.40	—	venice	✓
glm-4.7-flash	#28	$0.06	$0.40	—	venice	✓
qwen3-coder-480b-a35b	#32	$0.35	$1.50	$0.04	openrouter	—
gpt-oss-120b	#35	$0.07	$0.30	—	venice	✓
qwen3-235b-a22b-instruct-2507	#39	$0.15	$0.75	—	venice	✓
qwen3-vl-235b-a22b-instruct	#45	$0.21	$1.90	—	venice	✓
qwen3-vl-30b-a3b-instruct	#51	$0.25	$0.90	—	venice	✓
gemma-3-27b-it	#54	$0.12	$0.20	—	venice	✓
deepseek-v4-flash-0731	—	$0.17	$0.35	—	venice	✓
gpt-oss-20b	—	$0.05	$0.19	—	venice	✓
inkling	—	$1.25	$5.06	$0.21	modelsdev	—
llama-3.3-70b-instruct	—	$0.70	$2.80	—	venice	✓
mimo-v2.5	—	$0.40	$2.00	—	venice	✓
mistral-small-3.2-24b	—	$0.09	$0.25	—	venice	✓
nemotron-3-nano-30b-a3b	—	$0.07	$0.30	—	venice	✓
qwen3.5-9b	—	$0.10	$0.15	—	venice	✓
qwen3.8-2.4t-a95b	—	$2.50	$7.50	—	venice	✓

when (UTC)	model	change
Aug 31 22:56	kimi-k2.5	$/M input $0.53 → $0.56 ↑ 5.3% [source switch]
Aug 31 22:56	kimi-k2.5	$/M output $3.33 → $3.50 ↑ 5.3% [source switch]